Docling/docling/datamodel/settings.py
Christoph Auer 60dc852f16
feat: Updated Layout processing with forms and key-value areas (#530)
* Upgraded Layout Postprocessing, sending old code back to ERZ

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Implement hierachical cluster layout processing

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Pass nested cluster processing through full pipeline

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Pass nested clusters through GLM as payload

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Move to_docling_document from ds-glm to this repo

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Clean up imports again

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* feat(Accelerator): Introduce options to control the num_threads and device from API, envvars, CLI.
- Introduce the AcceleratorOptions, AcceleratorDevice and use them to set the device where the models run.
- Introduce the accelerator_utils with function to decide the device and resolve the AUTO setting.
- Refactor the way how the docling-ibm-models are called to match the new init signature of models.
- Translate the accelerator options to the specific inputs for third-party models.
- Extend the docling CLI with parameters to set the num_threads and device.
- Add new unit tests.
- Write new example how to use the accelerator options.

* fix: Improve the pydantic objects in the pipeline_options and imports.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: TableStructureModel: Refactor the artifacts path to use the new structure for fast/accurate model

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* Updated test ground-truth

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Updated test ground-truth (again), bugfix for empty layout

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Do proper check to set the device in EasyOCR, RapidOCR.

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: Correct the way to set GPU for EasyOCR, RapidOCR

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* fix: Ocr AccleratorDevice

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* Merge pull request #556 from DS4SD/cau/layout-processing-improvement

feat: layout processing improvements and bugfixes

* Update lockfile

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update tests

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update HF model ref, reset test generate

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Repin to release package versions

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Many layout processing improvements, add document index type

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update pinnings to docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix table box snapping

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for cluster pre-ordering

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Introduce OCR confidence, propagate to orphan in post-processing

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix form and key value area groups

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Adjust confidence in EasyOcr

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Roll back CLI changes from main

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update docling-core pinning

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Annoying fixes for historical python versions

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Updated test GT for legacy

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Comment cleanup

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Nikos Livathinos <nli@zurich.ibm.com>
2024-12-17 17:32:24 +01:00

51 lines
1.3 KiB
Python

import sys
from pathlib import Path
from pydantic import BaseModel
from pydantic_settings import BaseSettings, SettingsConfigDict
class DocumentLimits(BaseModel):
max_num_pages: int = sys.maxsize
max_file_size: int = sys.maxsize
class BatchConcurrencySettings(BaseModel):
doc_batch_size: int = 2
doc_batch_concurrency: int = 2
page_batch_size: int = 4
page_batch_concurrency: int = 2
elements_batch_size: int = 16
# doc_batch_size: int = 1
# doc_batch_concurrency: int = 1
# page_batch_size: int = 1
# page_batch_concurrency: int = 1
# model_concurrency: int = 2
# To force models into single core: export OMP_NUM_THREADS=1
class DebugSettings(BaseModel):
visualize_cells: bool = False
visualize_ocr: bool = False
visualize_layout: bool = False
visualize_raw_layout: bool = False
visualize_tables: bool = False
profile_pipeline_timings: bool = False
# Path used to output debug information.
debug_output_path: str = str(Path.cwd() / "debug")
class AppSettings(BaseSettings):
model_config = SettingsConfigDict(env_prefix="DOCLING_", env_nested_delimiter="_")
perf: BatchConcurrencySettings
debug: DebugSettings
settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings())